提升图数据分布外分类鲁棒性，缓解少数类性能下降与结构噪声影响。
Robust OOD Graph Learning via Mean Constraints and Noise Reduction
- 通过最坏情况下的相似性聚合优化少数类特征
- 动态重加权邻居结构一致性，降低噪声干扰
- 适用于存在类别不平衡的图学习任务
图模型在分布外（OOD）分类中常因类别不平衡和结构噪声导致性能骤降。本文针对两大挑战：一是标签分布偏斜导致少数类表现差，二是图数据对结构噪声敏感。提出两种互补方法：首先，约束均值优化（CMO）在最坏情况下通过相似性聚合增强少数类鲁棒性；其次，邻域感知噪声重加权（NNR）根据局部结构一致性为训练样本动态分配权重，减轻噪声影响。提供理论支持，并在合成与真实数据集上验证，显著提升图模型在分布外场景下的泛化能力与分类准确率。代码已公开于 https://anonymous.4open.science/r/CMO-NNR-2F30。
原文摘要 · Abstract (English)
Graph Out-of-Distribution (OOD) classification often suffers from sharp performance drops, particularly under category imbalance and structural noise. This work tackles two pressing challenges in this context: (1) the underperformance of minority classes due to skewed label distributions, and (2) their heightened sensitivity to structural noise in graph data. To address these problems, we propose two complementary solutions. First, Constrained Mean Optimization (CMO) improves minority class robustness by encouraging similarity-based instance aggregation under worst-case conditions. Second, the Neighbor-Aware Noise Reweighting (NNR) mechanism assigns dynamic weights to training samples based on local structural consistency, mitigating noise influence. We provide theoretical justification for our methods, and validate their effectiveness with extensive experiments on both synthetic and real-world datasets, showing significant improvements in Graph OOD generalization and classification accuracy. The code for our method is available at: https://anonymous.4open.science/r/CMO-NNR-2F30.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。